Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs
One of the most difficult challenges in providing a reliable and safe autonomous collision avoidance maneuver is developing the driver model that provides the planning system with the risk of an impending collision. Over the last few years, researchers have extensively studied several methodologies...
| Main Authors: | , , , , |
|---|---|
| Format: | Book Chapter |
| Language: | English English English |
| Published: |
Woodhead Publishing
2024
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/41786/1/Machine%20Intelligence%20in%20Mechanical%20Engineering.pdf http://umpir.ump.edu.my/id/eprint/41786/2/Human-like%20driver%20model%20for%20emergency%20collision%20avoidance_ABST.pdf http://umpir.ump.edu.my/id/eprint/41786/3/Human-like%20driver%20model%20for%20emergency%20collision%20avoidance.pdf |
| _version_ | 1811138490965950464 |
|---|---|
| author | Nurhaffizah, Hassan Mohd Hatta, Mohammad Ariff Hairi, Zamzuri Sarah ‘Atifah, Saruchi Nurbaiti, Wahid |
| author_facet | Nurhaffizah, Hassan Mohd Hatta, Mohammad Ariff Hairi, Zamzuri Sarah ‘Atifah, Saruchi Nurbaiti, Wahid |
| author_sort | Nurhaffizah, Hassan |
| collection | UMP |
| description | One of the most difficult challenges in providing a reliable and safe autonomous collision avoidance maneuver is developing the driver model that provides the planning system with the risk of an impending collision. Over the last few years, researchers have extensively studied several methodologies to develop such a driver model. The human-like driver model, on the other hand, is a rarely discussed research topic. This work aims to develop a steering maneuver model in emergency collision avoidance that can imitate human emergency intervention. The neural network autoregressive with exogenous inputs (NNARX) is utilized to develop the model and autonomously predict the steering angle response. The work begins by collecting the avoidance maneuver driving data of the expert driver from the automaker company. In the data collection process, a controlled environment target scenario is used to ensure that all drivers encounter real emergencies. To investigate the performance of the developed model, a comparison prediction performance between the developed model and feed-forward neural network (FFNN) is presented. The finding shows that NNARX predicts the steering angle response with a lower prediction error during both training and testing compared to FFNN. |
| first_indexed | 2024-09-25T03:51:02Z |
| format | Book Chapter |
| id | UMPir41786 |
| institution | Universiti Malaysia Pahang |
| language | English English English |
| last_indexed | 2024-09-25T03:51:02Z |
| publishDate | 2024 |
| publisher | Woodhead Publishing |
| record_format | dspace |
| spelling | UMPir417862024-07-03T03:37:43Z http://umpir.ump.edu.my/id/eprint/41786/ Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs Nurhaffizah, Hassan Mohd Hatta, Mohammad Ariff Hairi, Zamzuri Sarah ‘Atifah, Saruchi Nurbaiti, Wahid TJ Mechanical engineering and machinery TS Manufactures One of the most difficult challenges in providing a reliable and safe autonomous collision avoidance maneuver is developing the driver model that provides the planning system with the risk of an impending collision. Over the last few years, researchers have extensively studied several methodologies to develop such a driver model. The human-like driver model, on the other hand, is a rarely discussed research topic. This work aims to develop a steering maneuver model in emergency collision avoidance that can imitate human emergency intervention. The neural network autoregressive with exogenous inputs (NNARX) is utilized to develop the model and autonomously predict the steering angle response. The work begins by collecting the avoidance maneuver driving data of the expert driver from the automaker company. In the data collection process, a controlled environment target scenario is used to ensure that all drivers encounter real emergencies. To investigate the performance of the developed model, a comparison prediction performance between the developed model and feed-forward neural network (FFNN) is presented. The finding shows that NNARX predicts the steering angle response with a lower prediction error during both training and testing compared to FFNN. Woodhead Publishing 2024-01 Book Chapter PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/41786/1/Machine%20Intelligence%20in%20Mechanical%20Engineering.pdf pdf en http://umpir.ump.edu.my/id/eprint/41786/2/Human-like%20driver%20model%20for%20emergency%20collision%20avoidance_ABST.pdf pdf en http://umpir.ump.edu.my/id/eprint/41786/3/Human-like%20driver%20model%20for%20emergency%20collision%20avoidance.pdf Nurhaffizah, Hassan and Mohd Hatta, Mohammad Ariff and Hairi, Zamzuri and Sarah ‘Atifah, Saruchi and Nurbaiti, Wahid (2024) Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs. In: Machine Intelligence in Mechanical Engineering. Woodhead Publishing Reviews: Mechanical Engineering Series . Woodhead Publishing, Sawston, United Kingdom, 359 -377. ISBN 978-0-443-18644-8 https://doi.org/10.1016/B978-0-443-18644-8.00017-4 |
| spellingShingle | TJ Mechanical engineering and machinery TS Manufactures Nurhaffizah, Hassan Mohd Hatta, Mohammad Ariff Hairi, Zamzuri Sarah ‘Atifah, Saruchi Nurbaiti, Wahid Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| title | Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| title_full | Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| title_fullStr | Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| title_full_unstemmed | Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| title_short | Human-like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| title_sort | human like driver model for emergency collision avoidance using neural network autoregressive with exogenous inputs |
| topic | TJ Mechanical engineering and machinery TS Manufactures |
| url | http://umpir.ump.edu.my/id/eprint/41786/1/Machine%20Intelligence%20in%20Mechanical%20Engineering.pdf http://umpir.ump.edu.my/id/eprint/41786/2/Human-like%20driver%20model%20for%20emergency%20collision%20avoidance_ABST.pdf http://umpir.ump.edu.my/id/eprint/41786/3/Human-like%20driver%20model%20for%20emergency%20collision%20avoidance.pdf |
| work_keys_str_mv | AT nurhaffizahhassan humanlikedrivermodelforemergencycollisionavoidanceusingneuralnetworkautoregressivewithexogenousinputs AT mohdhattamohammadariff humanlikedrivermodelforemergencycollisionavoidanceusingneuralnetworkautoregressivewithexogenousinputs AT hairizamzuri humanlikedrivermodelforemergencycollisionavoidanceusingneuralnetworkautoregressivewithexogenousinputs AT sarahatifahsaruchi humanlikedrivermodelforemergencycollisionavoidanceusingneuralnetworkautoregressivewithexogenousinputs AT nurbaitiwahid humanlikedrivermodelforemergencycollisionavoidanceusingneuralnetworkautoregressivewithexogenousinputs |